基于多模态数据对比学习的重度抑郁症表征学习方法  

Multimodal data with contrastive learning for major depression disorder representation learning

作　　者：顾恒 马迪 马越 邵伟 张礼[1] GU Heng;MA Di;MA Yue;SHAO Wei;ZHANG Li(College of Information Science and Technology/Artificial Intelligence,Nanjing Forestry University,Nanjing 210042,Jiangsu,China;College of Integrated Traditional Chinese and Western Medicine,Jiangsu Health Vocational College,Nanjing 210018,Jiangsu,China;College of Computer Science and Technology/Artificial Intelligence/Software,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,Jiangsu,China)

机构地区：[1]南京林业大学信息科学技术学院/人工智能学院,江苏南京210042 [2]江苏卫生健康职业学院中西医结合学院,江苏南京210018 [3]南京航空航天大学计算机科学与技术学院/人工智能学院/软件学院,江苏南京210016

出　　处：《陕西师范大学学报(自然科学版)》2025年第1期12-21,共10页Journal of Shaanxi Normal University:Natural Science Edition

基　　金：国家自然科学基金青年项目(62306143)。

摘　　要：影像基因组学认为神经影像与基因之间存在着一定程度的相关性,利用遗传变异与影像数据进行疾病分析愈发受研究人员重视。在实践中,临床医生拥有的数据规模往往较小,但仍然希望使用深度学习来解决现实问题。考虑到不断扩大的数据规模与昂贵的标注成本,构建能够利用多模态数据的无监督学习方法十分必要。为了满足上述需求,提出了一种基于影像与基因多模态表格数据对比学习的表征学习方法(multimodal tabular data with contrastive learning,MTCL),该模型利用了静息态功能磁共振成像(rs-fMRI)和单核苷酸多态性(single nucleotide polymorphisms,SNP)数据,无需数据的任何标签信息。为了增强可解释性,模型先通过特征提取模块将rs-fMRI和SNP数据转换为表格类型结构,再通过多模态表格数据对比学习模块对多模态数据进行融合,并获得融合后的数据表征。在重度抑郁症(major depression disorder,MDD)数据上,文中提出的方法能够有效提升MDD诊断性能。此外,MTCL方法结合了模型归因方法挖掘与MDD相关的影像和遗传生物标记物,提高了模型的可解释性,有助于研究人员对疾病发病机制的理解。Imaging genetics suggests that there is a certain degree of correlation between neuroimaging and genes,leading researchers to pay attention to the analysis of diseases using genetic variations and imaging data.In practice,clinical doctors usually have limited data availability but still aspire to employ deep learning method for real-world problems.Considering the expanding data scale and expensive annotation costs,it becomes essential to develop an unsupervised learning method capable of utilizing multimodal data.To meet these needs,a representation learning method based on multimodal tabular data with contrastive learning(MTCL)is proposed.The model leverages resting-state functional magnetic resonance imaging(rs-fMRI)and single nucleotide polymorphisms(SNP)data without requiring any labeled information.To enhance interpretability,the model first transforms rs-fMRI and SNP data into a tabular structure through a feature extraction module.Then,a multimodal tabular data contrastive learning method is employed to fuse the dataset and obtain the fused data representation.On the dataset of major depressive disorder(MDD),our proposed method effectively improves the diagnostic performance of MDD.Additionally,the MTCL method combines model attribution techniques to explore imaging and genetic biomarkers associated with MDD,enhancing the interpretability of the model and aiding researchers in understanding the mechanisms underlying the disease.

关 键 词：对比学习 多模态数据 模型归因 重度抑郁症 诊断模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]